© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49650
    Prev
    Next
    INDEX
    Explanations

    code expression terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "But
    -0.12
     OK
    -0.11
     yes
    -0.11
    /welcome
    -0.11
     agreeing
    -0.11
     welcome
    -0.11
    yeah
    -0.11
    OK
    -0.11
     ok
    -0.11
     congratulations
    -0.11
    POSITIVE LOGITS
     answered
    0.10
    Answer
    0.10
     Answer
    0.10
     answers
    0.10
     answer
    0.09
     foc
    0.08
     uncertain
    0.08
     Depends
    0.08
     Answers
    0.08
     concentrates
    0.08
    Activations Density 0.077%

    No Known Activations